Processed and Anonymized Dataset for Microcephaly Prediction in Brazil (2015-2024): Integrating Clinical, Epidemiological, and Infrastructure Data

Abstract/Description: This dataset contains processed and anonymized records of suspected microcephaly cases in Brazil from 2015 to 2024, derived from the Public Health Event Registry (RESP), integrated with epidemiological data (Zika Virus from SINAN) and healthcare infrastructure data (CNES). Data Sources: RESP-Microcefalia (Ministry of Health, Brazil) SINAN (Notifiable Diseases Information System) CNES (National Register of Health Establishments) Anonymization Statement: In compliance with the Brazilian General Data Protection Law (LGPD), all direct identifiers (exact birth dates, notification dates, and municipality of residence) have been removed or generalized. Temporal Resolution: Aggregated by Epidemiological Week (SEMANA_EPI). Spatial Resolution: Aggregated by State (UFRES). Usage: This dataset is designed to reproduce the experiments described in the paper "Análise Preditiva e Generalização Temporal de Modelos de Ensemble para Classificação de Casos de Microcefalia no Brasil". Ideally, it should be used with the source code available at: github.com/deivyrossi/microcephaly_prediction_analysis